Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mention of numerical values or statistics related to study findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.49
     kira
    -0.47
    }{\
    -0.45
     tinta
    -0.44
     GU
    -0.44
     Power
    -0.42
    cody
    -0.42
     подо
    -0.41
    }]);
    -0.41
     memang
    -0.41
    POSITIVE LOGITS
    subsubsection
    0.96
     Jefus
    0.87
     kasarigan
    0.86
    EClass
    0.81
    شهاد
    0.77
    Hauptartikel
    0.73
     VIDEOTAPE
    0.70
     Efq
    0.69
     '\\;'
    0.69
    DockStyle
    0.68
    Act Density 0.469%

    No Known Activations